Challenge 9

Author

Jun Noh

Loading in libraries/dataset

Code
library(tidyverse)
library(here)
library(broom)
library(knitr)
library(kableExtra)
library(DT)
library(scales)
Code
babyNames <- read_csv(here::here("supporting_artifacts", "Extended Thinking", 
                                 "Challenge 9", "StateNames_A.csv")) |> 
  rename(Sex = "Gender")

1. Interactive dataset for babyNames

Code
datatable(babyNames)

2a. Summarizing & Visualizing the Number of Allisons - All

Code
babyNames |> 
  group_by(Sex, State) |> 
  filter(Name == "Allison") |> 
  summarize(Total = sum(Count)) |>
  pivot_wider(names_from = Sex, values_from = Total) |> 
  mutate(M = replace_na(M, 0), `F` = replace_na(`F`, 0)) |> 
  kable(caption = "<center><strong>Frequencies of babies named 
        Allison by state</strong></center>") |> 
  kable_styling(bootstrap_options = "striped", html_font = "Cambria") 
Frequencies of babies named Allison by state
State F M
AK 232 0
AL 1535 0
AR 1198 0
AZ 1880 0
CA 12413 0
CO 1594 0
CT 1099 0
DC 321 0
DE 294 0
FL 4455 0
GA 3257 0
HI 183 0
IA 1477 0
ID 451 0
IL 5110 0
IN 3067 0
KS 1283 0
KY 1905 20
LA 1209 0
MA 2218 0
MD 2229 0
ME 340 0
MI 4014 0
MN 2374 0
MO 2882 0
MS 817 0
MT 226 0
NC 3435 0
ND 285 0
NE 807 0
NH 412 0
NJ 3052 0
NM 399 0
NV 729 0
NY 5747 0
OH 5487 0
OK 1421 0
OR 1186 0
PA 4307 0
RI 306 0
SC 1228 0
SD 376 0
TN 2488 0
TX 10192 0
UT 1125 0
VA 3220 0
VT 135 0
WA 1956 0
WI 2367 0
WV 813 0
WY 142 0

2b. Summarizing & Visualizing the Number of Allisons - Female

Code
babyNames |> 
  mutate(Count = replace_na(Count, 0)) |> 
  group_by(Sex, State) |> 
  filter(Name == "Allison", Sex == "F") |> 
  summarize(Total = sum(Count)) |>
  kable(caption = "<center><strong>Frequencies of female babies named 
        Allison by state</strong></center>") |> 
  kable_styling(bootstrap_options = "striped", html_font = "Cambria") 
Frequencies of female babies named Allison by state
Sex State Total
F AK 232
F AL 1535
F AR 1198
F AZ 1880
F CA 12413
F CO 1594
F CT 1099
F DC 321
F DE 294
F FL 4455
F GA 3257
F HI 183
F IA 1477
F ID 451
F IL 5110
F IN 3067
F KS 1283
F KY 1905
F LA 1209
F MA 2218
F MD 2229
F ME 340
F MI 4014
F MN 2374
F MO 2882
F MS 817
F MT 226
F NC 3435
F ND 285
F NE 807
F NH 412
F NJ 3052
F NM 399
F NV 729
F NY 5747
F OH 5487
F OK 1421
F OR 1186
F PA 4307
F RI 306
F SC 1228
F SD 376
F TN 2488
F TX 10192
F UT 1125
F VA 3220
F VT 135
F WA 1956
F WI 2367
F WV 813
F WY 142

3. Alan dataset

Code
A_names <- babyNames |> 
  filter(Name %in% c("Alan", "Allen", "Allan"), Sex == "M")

4. Interactive dataset for A_names

Code
datatable(A_names)

5. Total Counts

Code
A_names |> 
  filter(State %in% c("CA", "PA"), Year == "2000") |> 
  pivot_wider(names_from = Name, values_from = Count) |> 
  mutate(across(Alan:Allan, .fns = replace_na, 0)) |> 
  rowwise() |> 
  mutate(Total = sum(Alan, Allen, Allan)) |> 
  select(-c(Year, Sex)) |> 
  kable(caption = "<center><strong>Total counts of Different Alan 
        spellings in CA and PA in 2000</strong></center>") |> 
  kable_styling(bootstrap_options = "striped", html_font = "Cambria") 
Total counts of Different Alan spellings in CA and PA in 2000
State Alan Allen Allan Total
CA 579 176 131 886
PA 51 56 12 119

6. Percentages

Code
A_names |> 
  filter(State %in% c("CA", "PA"), Year == "2000") |> 
  pivot_wider(names_from = Name, values_from = Count) |> 
  mutate(across(Alan:Allan, .fns = replace_na, 0)) |> 
  rowwise() |> 
  mutate(total = sum(Alan, Allen, Allan), Alan = percent(Alan/total), 
         Allen = percent(Allen/total), 
         Allan = percent(Allan/total)) |> 
  select(-c(total, Year, Sex)) |> 
  kable(caption = "<count><strong>Percentages of different Alan 
        spellings in CA and PA in 2000 rounded 
        to nearest whole number</strong></center>", 
        digits = 2) |> 
  kable_styling(bootstrap_options = "striped", html_font = "Cambria") 
Percentages of different Alan spellings in CA and PA in 2000 rounded to nearest whole number
State Alan Allen Allan
CA 65% 20% 15%
PA 43% 47% 10%